From 128ea9f6ccfb6960293ae4212f4f97165e42222d Mon Sep 17 00:00:00 2001 From: Marco Crivellari Date: Sat, 14 Jun 2025 15:35:29 +0200 Subject: [PATCH 1/2] workqueue: Add system_percpu_wq and system_dfl_wq Currently, if a user enqueue a work item using schedule_delayed_work() the used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to schedule_work() that is using system_wq and queue_work(), that makes use again of WORK_CPU_UNBOUND. This lack of consistentcy cannot be addressed without refactoring the API. system_wq is a per-CPU worqueue, yet nothing in its name tells about that CPU affinity constraint, which is very often not required by users. Make it clear by adding a system_percpu_wq. system_unbound_wq should be the default workqueue so as not to enforce locality constraints for random work whenever it's not required. Adding system_dfl_wq to encourage its use when unbound work should be used. Suggested-by: Tejun Heo Signed-off-by: Marco Crivellari Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 8 +++++--- kernel/workqueue.c | 13 +++++++++---- 2 files changed, 14 insertions(+), 7 deletions(-) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index b0dc957c3e56..74b0042709cd 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -427,7 +427,7 @@ enum wq_consts { /* * System-wide workqueues which are always present. * - * system_wq is the one used by schedule[_delayed]_work[_on](). + * system_percpu_wq is the one used by schedule[_delayed]_work[_on](). * Multi-CPU multi-threaded. There are users which expect relatively * short queue flush time. Don't queue works which can run for too * long. @@ -438,7 +438,7 @@ enum wq_consts { * system_long_wq is similar to system_wq but may host long running * works. Queue flushing might take relatively long. * - * system_unbound_wq is unbound workqueue. Workers are not bound to + * system_dfl_wq is unbound workqueue. Workers are not bound to * any specific CPU, not concurrency managed, and all queued works are * executed immediately as long as max_active limit is not reached and * resources are available. @@ -455,10 +455,12 @@ enum wq_consts { * system_bh[_highpri]_wq are convenience interface to softirq. BH work items * are executed in the queueing CPU's BH context in the queueing order. */ -extern struct workqueue_struct *system_wq; +extern struct workqueue_struct *system_wq; /* use system_percpu_wq, this will be removed */ +extern struct workqueue_struct *system_percpu_wq; extern struct workqueue_struct *system_highpri_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_unbound_wq; +extern struct workqueue_struct *system_dfl_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index cf6203282737..71a4dd59977c 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -505,12 +505,16 @@ static struct kthread_worker *pwq_release_worker __ro_after_init; struct workqueue_struct *system_wq __ro_after_init; EXPORT_SYMBOL(system_wq); +struct workqueue_struct *system_percpu_wq __ro_after_init; +EXPORT_SYMBOL(system_percpu_wq); struct workqueue_struct *system_highpri_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_long_wq); struct workqueue_struct *system_unbound_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_unbound_wq); +struct workqueue_struct *system_dfl_wq __ro_after_init; +EXPORT_SYMBOL_GPL(system_dfl_wq); struct workqueue_struct *system_freezable_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_wq); struct workqueue_struct *system_power_efficient_wq __ro_after_init; @@ -7816,10 +7820,11 @@ void __init workqueue_init_early(void) } system_wq = alloc_workqueue("events", 0, 0); + system_percpu_wq = alloc_workqueue("events", 0, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); - system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, - WQ_MAX_ACTIVE); + system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); + system_dfl_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", @@ -7830,8 +7835,8 @@ void __init workqueue_init_early(void) system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0); system_bh_highpri_wq = alloc_workqueue("events_bh_highpri", WQ_BH | WQ_HIGHPRI, 0); - BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || - !system_unbound_wq || !system_freezable_wq || + BUG_ON(!system_wq || !system_percpu_wq|| !system_highpri_wq || !system_long_wq || + !system_unbound_wq || !system_freezable_wq || !system_dfl_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq || !system_bh_wq || !system_bh_highpri_wq); From 930c2ea566aff59e962c50b2421d5fcc3b98b8be Mon Sep 17 00:00:00 2001 From: Marco Crivellari Date: Sat, 14 Jun 2025 15:35:30 +0200 Subject: [PATCH 2/2] workqueue: Add new WQ_PERCPU flag Currently if a user enqueue a work item using schedule_delayed_work() the used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to schedule_work() that is using system_wq and queue_work(), that makes use again of WORK_CPU_UNBOUND. This lack of consistentcy cannot be addressed without refactoring the API. This patch adds a new WQ_PERCPU flag to explicitly request the use of the per-CPU behavior. Both flags coexist for one release cycle to allow callers to transition their calls. Once migration is complete, WQ_UNBOUND can be removed and unbound will become the implicit default. tj: Merged doc patch. Suggested-by: Tejun Heo Signed-off-by: Marco Crivellari Signed-off-by: Tejun Heo --- Documentation/core-api/workqueue.rst | 6 ++++++ include/linux/workqueue.h | 1 + 2 files changed, 7 insertions(+) diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index e295835fc116..165ca73e8351 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -183,6 +183,12 @@ resources, scheduled and executed. BH work items cannot sleep. All other features such as delayed queueing, flushing and canceling are supported. +``WQ_PERCPU`` + Work items queued to a per-cpu wq are bound to a specific CPU. + This flag is the right choice when cpu locality is important. + + This flag is the complement of ``WQ_UNBOUND``. + ``WQ_UNBOUND`` Work items queued to an unbound wq are served by the special worker-pools which host workers which are not bound to any diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 74b0042709cd..f19072605faa 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -401,6 +401,7 @@ enum wq_flags { * http://thread.gmane.org/gmane.linux.kernel/1480396 */ WQ_POWER_EFFICIENT = 1 << 7, + WQ_PERCPU = 1 << 8, /* bound to a specific cpu */ __WQ_DESTROYING = 1 << 15, /* internal: workqueue is destroying */ __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */